Changed from the base model. Weights are Project Maya's Maya-M quant of GLM-5.3-Flash, unchanged. Adds a 2.2 MB vector (3 refusal directions per layer, layers 1 to 44) and a Maya engine patch that removes them at run time.
Base model: peasantsmith/GLM-5.3-Flash-Maya-GGUF
Where these bytes come from
Publisher at the pinned commit→You
Sources are tried in order. A file counts only when its size and sha256 match the manifest. Sources are checked when you ask for them, not on a timer.
Sources
Badge
Host
Last check
Result
From source
huggingface.co
2026-11-14 15:35 UTC
passed
Model card
From the publisher at commit 3518a2d. Shown as plain text with links; images open at the publisher.
Project Maya's Maya-M quant of GLM-5.3-Flash plus a 2.2 MB vector that removes refusals while the model runs, and a small patch for the Maya engine that applies it. On 4x RTX 3090 it decodes 56 tokens/s at a 256K context with the vector on.
The model weights in this repo are not mine. They are Maya-M and the vision files of Project Maya, copied byte for byte from peasantsmith/GLM-5.3-Flash-Maya-GGUF at revision 3e9f3bb20aa191e01c6fb850faf132d8149da98a. The SHA256 of all 5 files match theirs at that revision. See SHA256SUMS.
The authors changed the first shard after I downloaded it. Their commit 1084950a renames the architecture in the GGUF header to glm5-next, and the file size is the same. This repo has the earlier first shard, the one all my runs used with Maya v1.0.27. For the current files go to their repo.
My part is one file, vector/glm53-refusal-per-block-3dir.layers45.f32, a patch for the Maya engine that reads it, and the measurements below. For the original card, the other sizes (Maya-S, Maya-S24, Maya-L) and the authors' own benchmarks go to their repo.
The GGUF stays as its authors published it. Before each layer's FFN output is written into the 4 hyper-connection streams, the patched engine removes that layer's 3 directions from both operands of the write:
x = x - (x . v) v for each of the layer's directions v
Layers 1 to 44 each have 3 directions of their own. The first is harmful minus harmless at the last prompt token with thinking off, the second is the same with thinking on, and the third is the same at the closing </think> of the stock model's own reasoning. Without the setting the engine runs the original model.
The directions were not found on Maya-M. I found them on the EXL3 2.05 bpw quant of the same model with my exllamav3 fork and converted the file for Maya. The method and the scripts are in the abliteration write-up.
The file is raw float32 with 45 x 3 x 4096 values, 2,211,840 bytes, SHA256 b0debc326b06c956039fd75dc1cb759dd46c4aa5e868bbfef1a5b0607c3552b7.
64 held-out AdvBench and 82 JailbreakBench requests without thinking plus the first 32 with thinking: 178 answers, greedy, through the API of the running server, judged by the stock GLM-5.3-Flash.
Refused
Disputes the premise
Cut off while thinking
Maya-M with the vector
2
4
0
The 2 refusals are requests about suicide and self-harm. The model turns them into text about prevention. I left them as they are. "Disputes the premise" means the model takes the request and says its premise is false, as with a request to prove the Earth is flat.
On the EXL3 2.05 bpw quant, where the directions come from, the stock model refused 144 of 146 requests without thinking, and with the vector 0 of 438 answers were refusals. I did not run the stock Maya-M on these sets.
Maya v1.0.27, Maya-M, 256K context, after ./maya.sh --calibrate. Through the chat API, answers run to their natural end, thinking off, temperature 0. Maya serves 1 request at a time.
Without the vector
With the vector
Decode
58.4 tokens/s
56.1
Decode at 32K depth
57.2
55.9
Prefill at 8K
1078 to 1113 tokens/s
1119 to 1153
Prefill at 32K
1860 to 1896
1938 to 1953
Before calibration the same install gave 24.9 tokens/s. The engine had sent cold experts to the CPU, and my machine has only 2 memory channels. ./maya.sh --calibrate moved them to the PCIe path (STRATA_GLM_PCIE_SHARE=0.75).
Closeness to the original on a 25-window panel of BF16 logits (51,175 positions, full vocabulary), without the vector, computed by the Maya engine itself:
Quant
Size
KLD to BF16
Top-1 agreement
EXL3 2.05 bpw
85.1 GB
0.1214
88.68%
EXL3 mix, gate/up 2 bits and down 3 bits
98.1 GB
0.0959
89.87%
Maya-M
116.0 GB
0.0934
90.68%
EXL3 3.05 bpw
125.2 GB
0.0473
93.08%
The EXL3 rows ran through exllamav3 and the Maya-M row through Maya, so the Maya number includes the noise of its own engine. The authors measure Maya-M against FP8 on their own set, and those numbers are not comparable with this table. I did not measure KLD of Maya-M with the vector on.
The fork is Maya v1.0.27 plus 3 files. tools/glm_ablate_config.py maya-maya-m.json --off gives the original model back. The settings are STRATA_GLM_ABLATE (the file) and STRATA_GLM_ABLATE_LAYERS=45 in the env section of the config. Details: docs/GLM-ABLATE.md.
Upstream Maya without the patch runs these GGUF files as the original model and ignores the vector.
alesha-pro <huggingface.co/alesha-pro>Newsgroups: alt.freeweights.abliteratedSubject: 
mlx-community